Respeak: Enhancing Speech Transcription for Underrepresented Languages (Full Transcript)

Respeak leverages crowdsourcing and ASR to improve transcription of languages like Hindi and Indian-accented English, boosting quality and income potential.

Download Transcript (DOCX)

Respeak A Voice-based, Crowd-powered Speech Transcription System

Added on 09/06/2024

Speakers

Add new speaker

Speaker 1: We present Respeak, a voice-based, crowd-powered speech transcription system. Respeak combines crowdsourcing and ASR to improve speech transcription of underrepresented languages and accents, such as Hindi and Indian-accented English. Users speak, rather than type, to transcribe audio tasks with their smartphone. We deployed Respeak in India with 25 users and found it improved transcription quality while enhancing earning potential of low-income people.

Summary

Generate a brief summary highlighting the main points of the transcript.

Title

Generate a concise and relevant title for the transcript based on the main themes and content discussed.

Keywords

Identify and highlight the key words or phrases most relevant to the content of the transcript.

Key Takeaways

Extract key takeaways from the content of the transcript.

Sentiments

Analyze the emotional tone of the transcript to determine whether the sentiment is positive, negative, or neutral.

Enter your query

{{ secondsToHumanTime(time) }}

Back

Forward

{{ Math.round(speed * 100) / 100 }}x

{{ secondsToHumanTime(duration) }}

Select Audio file